PyTorchKR Papers

최신 논문

총 590편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2006.10859공식 코드 · Papers with Code

MARS: Masked Automatic Ranks Selection in Tensor Decompositions

Tensor decomposition methods have proven effective in various applications, including compression and acceleration of neural networks. At the same time, the problem of determining optimal decomposition ranks, which present the crucial parameter controlling the compression-accuracy trade-off, is still acute. In this paper, we introduce MARS -- a new efficient method for the automatic selection of ranks in general tensor decompositions. During training, the procedure learns binary masks over decomposition cores that "select" the optimal tensor structure. The learning is performed via relaxed maximum a posteriori (MAP) estimation in a specific Bayesian model and can be naturally embedded into the standard neural network training routine. Diverse experiments demonstrate that MARS achieves better results compared to previous works in various tasks.

arXiv:2006.10021공식 코드 · Papers with Code

Generalising Recursive Neural Models by Tensor Decomposition

Most machine learning models for structured data encode the structural knowledge of a node by leveraging simple aggregation functions (in neural models, typically a weighted sum) of the information in the node's neighbourhood. Nevertheless, the choice of simple context aggregation functions, such as the sum, can be widely sub-optimal. In this work we introduce a general approach to model aggregation of structural context leveraging a tensor-based formulation. We show how the exponential growth in the size of the parameter space can be controlled through an approximation based on the Tucker tensor decomposition. This approximation allows limiting the parameters space size, decoupling it from its strict relation with the size of the hidden encoding space. By this means, we can effectively regulate the trade-off between expressivity of the encoding, controlled by the hidden size, computational complexity and model generalisation, influenced by parameterisation. Finally, we introduce a new Tensorial Tree-LSTM derived as an instance of our framework and we use it to experimentally assess our working hypotheses on tree classification scenarios.

arXiv:2006.08183

Computing Large-Scale Matrix and Tensor Decomposition with Structured Factors: A Unified Nonconvex Optimization Perspective

The proposed article aims at offering a comprehensive tutorial for the computational aspects of structured matrix and tensor factorization. Unlike existing tutorials that mainly focus on {\it algorithmic procedures} for a small set of problems, e.g., nonnegativity or sparsity-constrained factorization, we take a {\it top-down} approach: we start with general optimization theory (e.g., inexact and accelerated block coordinate descent, stochastic optimization, and Gauss-Newton methods) that covers a wide range of factorization problems with diverse constraints and regularization terms of engineering interest. Then, we go `under the hood' to showcase specific algorithm design under these introduced principles. We pay a particular attention to recent algorithmic developments in structured tensor and matrix factorization (e.g., random sketching and adaptive step size based stochastic optimization and structure-exploiting second-order algorithms), which are the state of the art---yet much less touched upon in the literature compared to {\it block coordinate descent} (BCD)-based methods. We expect that the article to have an educational values in the field of structured factorization and hope to stimulate more research in this important and exciting direction.

arXiv:2006.03669

An Overview of Neural Network Compression

Overparameterized networks trained to convergence have shown impressive performance in domains such as computer vision and natural language processing. Pushing state of the art on salient tasks within these domains corresponds to these models becoming larger and more difficult for machine learning practitioners to use given the increasing memory and storage requirements, not to mention the larger carbon footprint. Thus, in recent years there has been a resurgence in model compression techniques, particularly for deep convolutional neural networks and self-attention based networks such as the Transformer. Hence, this paper provides a timely overview of both old and current compression techniques for deep neural networks, including pruning, quantization, tensor decomposition, knowledge distillation and combinations thereof. We assume a basic familiarity with deep learning architectures\footnote{For an introduction to deep learning, see ~\citet{goodfellow2016deep}}, namely, Recurrent Neural Networks~\citep[(RNNs)][]{rumelhart1985learning,hochreiter1997long}, Convolutional Neural Networks~\citep{fukushima1980neocognitron}~\footnote{For an up to date overview see~\citet{khan2019survey}} and Self-Attention based networks~\citep{vaswani2017attention}\footnote{For a general overview of self-attention networks, see ~\citet{chaudhari2019attentive}.},\footnote{For more detail and their use in natural language processing, see~\citet{hu2019introductory}}. Most of the papers discussed are proposed in the context of at least one of these DNN architectures.

arXiv:2005.13746공식 코드 · Papers with Code

Tensor decomposition to Compress Convolutional Layers in Deep Learning

Feature extraction for tensor data serves as an important step in many tasks such as anomaly detection, process monitoring, image classification, and quality control. Although many methods have been proposed for tensor feature extraction, there are still two challenges that need to be addressed: 1) how to reduce the computation cost for high dimensional and large volume tensor data; 2) how to interpret the output features and evaluate their significance. {The most recent methods in deep learning, such as Convolutional Neural Network (CNN), have shown outstanding performance in analyzing tensor data, but their wide adoption is still hindered by model complexity and lack of interpretability. To fill this research gap, we propose to use CP-decomposition to approximately compress the convolutional layer (CPAC-Conv layer) in deep learning. The contributions of our work could be summarized into three aspects: (1) we adapt CP-decomposition to compress convolutional kernels and derive the expressions of both forward and backward propagations for our proposed CPAC-Conv layer; (2) compared with the original convolutional layer, the proposed CPAC-Conv layer can reduce the number of parameters without decaying prediction performance. It can combine with other layers to build novel deep Neural Networks; (3) the value of decomposed kernels indicates the significance of the corresponding feature map, which provides us with insights to guide feature selection.

arXiv:2005.13706

Tensor Decomposition for Multi-agent Predictive State Representation

Predictive state representation~(PSR) uses a vector of action-observation sequence to represent the system dynamics and subsequently predicts the probability of future events. It is a concise knowledge representation that is well studied in a single-agent planning problem domain. To the best of our knowledge, there is no existing work on using PSR to solve multi-agent planning problems. Learning a multi-agent PSR model is quite difficult especially with the increasing number of agents, not to mention the complexity of a problem domain. In this paper, we resort to tensor techniques to tackle the challenging task of multi-agent PSR model development problems. By first focusing on a two-agent setting, we construct the system dynamics matrix as a high order tensor for a PSR model, learn the prediction parameters and deduce state vectors directly through two different tensor decomposition methods respectively, and derive the transition parameters via linear regression. Subsequently, we generalize the PSR learning approaches in a multi-agent setting. Experimental results show that our methods can effectively solve multi-agent PSR modelling problems in multiple problem domains.

arXiv:2005.11914

Deep Tensor CCA for Multi-view Learning

We present Deep Tensor Canonical Correlation Analysis (DTCCA), a method to learn complex nonlinear transformations of multiple views (more than two) of data such that the resulting representations are linearly correlated in high order. The high-order correlation of given multiple views is modeled by covariance tensor, which is different from most CCA formulations relying solely on the pairwise correlations. Parameters of transformations of each view are jointly learned by maximizing the high-order canonical correlation. To solve the resulting problem, we reformulate it as the best sum of rank-1 approximation, which can be efficiently solved by existing tensor decomposition method. DTCCA is a nonlinear extension of tensor CCA (TCCA) via deep networks. The transformations of DTCCA are parametric functions, which are very different from implicit mapping in the form of kernel function. Comparing with kernel TCCA, DTCCA not only can deal with arbitrary dimensions of the input data, but also does not need to maintain the training data for computing representations of any given data point. Hence, DTCCA as a unified model can efficiently overcome the scalable issue of TCCA for either high-dimensional multi-view data or a large amount of views, and it also naturally extends TCCA for learning nonlinear representation. Extensive experiments on three multi-view data sets demonstrate the effectiveness of the proposed method.

arXiv:2005.04605

Robust Tensor Decomposition for Image Representation Based on Generalized Correntropy

Traditional tensor decomposition methods, e.g., two dimensional principal component analysis and two dimensional singular value decomposition, that minimize mean square errors, are sensitive to outliers. To overcome this problem, in this paper we propose a new robust tensor decomposition method using generalized correntropy criterion (Corr-Tensor). A Lagrange multiplier method is used to effectively optimize the generalized correntropy objective function in an iterative manner. The Corr-Tensor can effectively improve the robustness of tensor decomposition with the existence of outliers without introducing any extra computational cost. Experimental results demonstrated that the proposed method significantly reduces the reconstruction error on face reconstruction and improves the accuracies on handwritten digit recognition and facial image clustering.

arXiv:2005.04567

Non-recurrent Traffic Congestion Detection with a Coupled Scalable Bayesian Robust Tensor Factorization Model

Non-recurrent traffic congestion (NRTC) usually brings unexpected delays to commuters. Hence, it is critical to accurately detect and recognize the NRTC in a real-time manner. The advancement of road traffic detectors and loop detectors provides researchers with a large-scale multivariable temporal-spatial traffic data, which allows the deep research on NRTC to be conducted. However, it remains a challenging task to construct an analytical framework through which the natural spatial-temporal structural properties of multivariable traffic information can be effectively represented and exploited to better understand and detect NRTC. In this paper, we present a novel analytical training-free framework based on coupled scalable Bayesian robust tensor factorization (Coupled SBRTF). The framework can couple multivariable traffic data including traffic flow, road speed, and occupancy through sharing a similar or the same sparse structure. And, it naturally captures the high-dimensional spatial-temporal structural properties of traffic data by tensor factorization. With its entries revealing the distribution and magnitude of NRTC, the shared sparse structure of the framework compasses sufficiently abundant information about NRTC. While the low-rank part of the framework, expresses the distribution of general expected traffic condition as an auxiliary product. Experimental results on real-world traffic data show that the proposed method outperforms coupled Bayesian robust principal component analysis (coupled BRPCA), the rank sparsity tensor decomposition (RSTD), and standard normal deviates (SND) in detecting NRTC. The proposed method performs even better when only traffic data in weekdays are utilized, and hence can provide more precise estimation of NRTC for daily commuters.

arXiv:2005.04366

Compressing Recurrent Neural Networks Using Hierarchical Tucker Tensor Decomposition

Recurrent Neural Networks (RNNs) have been widely used in sequence analysis and modeling. However, when processing high-dimensional data, RNNs typically require very large model sizes, thereby bringing a series of deployment challenges. Although the state-of-the-art tensor decomposition approaches can provide good model compression performance, these existing methods are still suffering some inherent limitations, such as restricted representation capability and insufficient model complexity reduction. To overcome these limitations, in this paper we propose to develop compact RNN models using Hierarchical Tucker (HT) decomposition. HT decomposition brings strong hierarchical structure to the decomposed RNN models, which is very useful and important for enhancing the representation capability. Meanwhile, HT decomposition provides higher storage and computational cost reduction than the existing tensor decomposition approaches for RNN compression. Our experimental results show that, compared with the state-of-the-art compressed RNN models, such as TT-LSTM, TR-LSTM and BT-LSTM, our proposed HT-based LSTM (HT-LSTM), consistently achieves simultaneous and significant increases in both compression ratio and test accuracy on different datasets.

arXiv:2005.01995

Adaptive Low-Rank Factorization to regularize shallow and deep neural networks

The overfitting is one of the cursing subjects in the deep learning field. To solve this challenge, many approaches were proposed to regularize the learning models. They add some hyper-parameters to the model to extend the generalization; however, it is a hard task to determine these hyper-parameters and a bad setting diverges the training process. In addition, most of the regularization schemes decrease the learning speed. Recently, Tai et al. [1] proposed low-rank tensor decomposition as a constrained filter for removing the redundancy in the convolution kernels of CNN. With a different viewpoint, we use Low-Rank matrix Factorization (LRF) to drop out some parameters of the learning model along the training process. However, this scheme similar to [1] probably decreases the training accuracy when it tries to decrease the number of operations. Instead, we use this regularization scheme adaptively when the complexity of a layer is high. The complexity of any layer can be evaluated by the nonlinear condition numbers of its learning system. The resulted method entitled "AdaptiveLRF" neither decreases the training speed nor vanishes the accuracy of the layer. The behavior of AdaptiveLRF is visualized on a noisy dataset. Then, the improvements are presented on some small-size and large-scale datasets. The preference of AdaptiveLRF on famous dropout regularizers on shallow networks is demonstrated. Also, AdaptiveLRF competes with dropout and adaptive dropout on the various deep networks including MobileNet V2, ResNet V2, DenseNet, and Xception. The best results of AdaptiveLRF on SVHN and CIFAR-10 datasets are 98%, 94.1% F-measure, and 97.9%, 94% accuracy. Finally, we state the usage of the LRF-based loss function to improve the quality of the learning model.

arXiv:2005.01538

A Solution for Large Scale Nonlinear Regression with High Rank and Degree at Constant Memory Complexity via Latent Tensor Reconstruction

This paper proposes a novel method for learning highly nonlinear, multivariate functions from examples. Our method takes advantage of the property that continuous functions can be approximated by polynomials, which in turn are representable by tensors. Hence the function learning problem is transformed into a tensor reconstruction problem, an inverse problem of the tensor decomposition. Our method incrementally builds up the unknown tensor from rank-one terms, which lets us control the complexity of the learned model and reduce the chance of overfitting. For learning the models, we present an efficient gradient-based algorithm that can be implemented in linear time in the sample size, order, rank of the tensor and the dimension of the input. In addition to regression, we present extensions to classification, multi-view learning and vector-valued output as well as a multi-layered formulation. The method can work in an online fashion via processing mini-batches of the data with constant memory complexity. Consequently, it can fit into systems equipped only with limited resources such as embedded systems or mobile phones. Our experiments demonstrate a favorable accuracy and running time compared to competing methods.

arXiv:2004.11022

Long-Short Term Spatiotemporal Tensor Prediction for Passenger Flow Profile

Spatiotemporal data is very common in many applications, such as manufacturing systems and transportation systems. It is typically difficult to be accurately predicted given intrinsic complex spatial and temporal correlations. Most of the existing methods based on various statistical models and regularization terms, fail to preserve innate features in data alongside their complex correlations. In this paper, we focus on a tensor-based prediction and propose several practical techniques to improve prediction. For long-term prediction specifically, we propose the "Tensor Decomposition + 2-Dimensional Auto-Regressive Moving Average (2D-ARMA)" model, and an effective way to update prediction real-time; For short-term prediction, we propose to conduct tensor completion based on tensor clustering to avoid oversimplifying and ensure accuracy. A case study based on the metro passenger flow data is conducted to demonstrate the improved performance.

arXiv:2004.09655

Network Anomaly Detection based on Tensor Decomposition

The problem of detecting anomalies in time series from network measurements has been widely studied and is a topic of fundamental importance. Many anomaly detection methods are based on packet inspection collected at the network core routers, with consequent disadvantages in terms of computational cost and privacy. We propose an alternative method in which packet header inspection is not needed. The method is based on the extraction of a normal subspace obtained by the tensor decomposition technique considering the correlation between different metrics. We propose a new approach for online tensor decomposition where changes in the normal subspace can be tracked efficiently. Another advantage of our proposal is the interpretability of the obtained models. The flexibility of the method is illustrated by applying it to two distinct examples, both using actual data collected on residential routers.

arXiv:2004.07984

Spectral Learning on Matrices and Tensors

Spectral methods have been the mainstay in several domains such as machine learning and scientific computing. They involve finding a certain kind of spectral decomposition to obtain basis functions that can capture important structures for the problem at hand. The most common spectral method is the principal component analysis (PCA). It utilizes the top eigenvectors of the data covariance matrix, e.g. to carry out dimensionality reduction. This data pre-processing step is often effective in separating signal from noise. PCA and other spectral techniques applied to matrices have several limitations. By limiting to only pairwise moments, they are effectively making a Gaussian approximation on the underlying data and fail on data with hidden variables which lead to non-Gaussianity. However, in most data sets, there are latent effects that cannot be directly observed, e.g., topics in a document corpus, or underlying causes of a disease. By extending the spectral decomposition methods to higher order moments, we demonstrate the ability to learn a wide range of latent variable models efficiently. Higher-order moments can be represented by tensors, and intuitively, they can encode more information than just pairwise moment matrices. More crucially, tensor decomposition can pick up latent effects that are missed by matrix methods, e.g. uniquely identify non-orthogonal components. Exploiting these aspects turns out to be fruitful for provable unsupervised learning of a wide range of latent variable models. We also outline the computational techniques to design efficient tensor decomposition methods. We introduce Tensorly, which has a simple python interface for expressing tensor operations. It has a flexible back-end system supporting NumPy, PyTorch, TensorFlow and MXNet amongst others, allowing multi-GPU and CPU operations and seamless integration with deep-learning functionalities.

arXiv:2003.08844

NeCPD: An Online Tensor Decomposition with Optimal Stochastic Gradient Descent

Multi-way data analysis has become an essential tool for capturing underlying structures in higher-order datasets stored in tensor $\mathcal{X} \in \mathbb{R} ^{I_1 \times \dots \times I_N} $. $CANDECOMP/PARAFAC$ (CP) decomposition has been extensively studied and applied to approximate $\mathcal{X}$ by $N$ loading matrices $A^{(1)}, \dots, A^{(N)}$ where $N$ represents the order of the tensor. We propose a new efficient CP decomposition solver named NeCPD for non-convex problem in multi-way online data based on stochastic gradient descent (SGD) algorithm. SGD is very useful in online setting since it allows us to update $\mathcal{X}^{(t+1)}$ in one single step. In terms of global convergence, it is well known that SGD stuck in many saddle points when it deals with non-convex problems. We study the Hessian matrix to identify theses saddle points, and then try to escape them using the perturbation approach which adds little noise to the gradient update step. We further apply Nesterov's Accelerated Gradient (NAG) method in SGD algorithm to optimally accelerate the convergence rate and compensate Hessian computational delay time per epoch. Experimental evaluation in the field of structural health monitoring using laboratory-based and real-life structural datasets show that our method provides more accurate results compared with existing online tensor analysis methods.

arXiv:2003.00895공식 코드 · Papers with Code

Revisiting Convolutional Neural Networks for Citywide Crowd Flow Analytics

Citywide crowd flow analytics is of great importance to smart city efforts. It aims to model the crowd flow (e.g., inflow and outflow) of each region in a city based on historical observations. Nowadays, Convolutional Neural Networks (CNNs) have been widely adopted in raster-based crowd flow analytics by virtue of their capability in capturing spatial dependencies. After revisiting CNN-based methods for different analytics tasks, we expose two common critical drawbacks in the existing uses: 1) inefficiency in learning global spatial dependencies, and 2) overlooking latent region functions. To tackle these challenges, in this paper we present a novel framework entitled DeepLGR that can be easily generalized to address various citywide crowd flow analytics problems. This framework consists of three parts: 1) a local feature extraction module to learn representations for each region; 2) a global context module to extract global contextual priors and upsample them to generate the global features; and 3) a region-specific predictor based on tensor decomposition to provide customized predictions for each region, which is very parameter-efficient compared to previous methods. Extensive experiments on two typical crowd flow analytics tasks demonstrate the effectiveness, stability, and generality of our framework.

arXiv:2002.12913

Applying Tensor Decomposition to image for Robustness against Adversarial Attack

Nowadays the deep learning technology is growing faster and shows dramatic performance in computer vision areas. However, it turns out a deep learning based model is highly vulnerable to some small perturbation called an adversarial attack. It can easily fool the deep learning model by adding small perturbations. On the other hand, tensor decomposition method widely uses for compressing the tensor data, including data matrix, image, etc. In this paper, we suggest combining tensor decomposition for defending the model against adversarial example. We verify this idea is simple and effective to resist adversarial attack. In addition, this method rarely degrades the original performance of clean data. We experiment on MNIST, CIFAR10 and ImageNet data and show our method robust on state-of-the-art attack methods.

arXiv:2002.12663

HOTCAKE: Higher Order Tucker Articulated Kernels for Deeper CNN Compression

The emerging edge computing has promoted immense interests in compacting a neural network without sacrificing much accuracy. In this regard, low-rank tensor decomposition constitutes a powerful tool to compress convolutional neural networks (CNNs) by decomposing the 4-way kernel tensor into multi-stage smaller ones. Building on top of Tucker-2 decomposition, we propose a generalized Higher Order Tucker Articulated Kernels (HOTCAKE) scheme comprising four steps: input channel decomposition, guided Tucker rank selection, higher order Tucker decomposition and fine-tuning. By subjecting each CONV layer to HOTCAKE, a highly compressed CNN model with graceful accuracy trade-off is obtained. Experiments show HOTCAKE can compress even pre-compressed models and produce state-of-the-art lightweight networks.

arXiv:2002.10252

TensorShield: Tensor-based Defense Against Adversarial Attacks on Images

Recent studies have demonstrated that machine learning approaches like deep neural networks (DNNs) are easily fooled by adversarial attacks. Subtle and imperceptible perturbations of the data are able to change the result of deep neural networks. Leveraging vulnerable machine learning methods raises many concerns especially in domains where security is an important factor. Therefore, it is crucial to design defense mechanisms against adversarial attacks. For the task of image classification, unnoticeable perturbations mostly occur in the high-frequency spectrum of the image. In this paper, we utilize tensor decomposition techniques as a preprocessing step to find a low-rank approximation of images which can significantly discard high-frequency perturbations. Recently a defense framework called Shield could "vaccinate" Convolutional Neural Networks (CNN) against adversarial examples by performing random-quality JPEG compressions on local patches of images on the ImageNet dataset. Our tensor-based defense mechanism outperforms the SLQ method from Shield by 14% against FastGradient Descent (FGSM) adversarial attacks, while maintaining comparable speed.